procoder go.instructions.md

A set of coding rules for a Go command-line tool, where the program's printed output, file paths, arguments, and exit codes are treated as its public interface.

In plain words
What is it for?
Use it when developing or reviewing the procoder Go CLI, especially its checks, error handling, output messages, and command-line behavior.
Why use it?
It prevents failed or skipped checks from appearing successful and keeps error messages useful. It also makes changes safer by preserving the tool's externally visible behavior.

Instructions file for GitHub Copilot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/azrtydxb/procoder/go
Clone the repo
git clone --depth 1 https://github.com/azrtydxb/procoder

Made for: GitHub Copilot.

Per session 924 This file is loaded in full into every session.
When invoked 924 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00924 $0.00924
Opus 5 $0.00462 $0.00462
Sonnet 5 $0.00185 $0.00185
Haiku 4.5 $0.00092 $0.00092

Measured yesterday against content hash 2c9912b095e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

procoder go.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/instructions/go.instructions.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go in procoder

Procoder is a Go CLI plus an agent layer. cmd/procoder/main.go is the dispatch and every domain lives under internal/<domain>/. The rules below are not style preferences — each one is here because breaking it produced a defect that shipped.

No silent green

The rule the whole tool is built on: a check that could not run must never read as one that passed.

  • A tool that is absent, a file that could not be read, a scanner that crashed — each is reported as NOT checked, naming the reason, and it fails the gate exactly as a real finding would.
  • Never return nil findings on an error path. if err != nil { return nil } is the shape that hides a whole domain.
  • An empty result is not a clean result. If a check scanned zero files, say so; do not print "0 finding(s)", which is what a clean scan prints.
  • When a tool fails, quote its last line of stderr, not its first. Scanners log progress first and the reason they gave up last, so the first line produced "dependencies were NOT checked: Starting filesystem walk for root: /" — alarming, and not the reason. Fall back to the exit status only when stderr is empty.

P-CONTROL: the binary prints, the agent writes

No command may modify a file in the repository it is checking. procoder format prints the formatted result for review. The one exception is procoder's own state under .procoder/, written by controllers that say so, and --save/--yes flags where writing is the whole point of the flag.

Paths and arguments

  • A command taking paths must honour them. procoder security <dir> scanned the change set and ignored its argument, so a person who named a directory was told "0 finding(s)" about files nobody opened.
  • Expand a directory argument to its files. Checks that work file by file silently do nothing with an unexpanded directory.
  • Resolve relative paths against the repository root, not the process directory — procoder can be run from a subdirectory, and gitx.ChangedFiles hands out absolute paths, so mixing the two makes a check scan nothing.
  • A flag a command does not implement is a usage error (exit 2), never a path. Every flag lives in knownFlags in cmd/procoder/flags.go, and a test holds that table against the literals main.go compares.

Read the full file on GitHub · 88 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 88 lines · 924 tokens per session scan A 2c9912b095e7

Subscribe to this mod's changes

procoder go.instructions.md is an instructions file published in the GitHub repository azrtydxb/procoder (196 stars, last pushed 2d ago), licensed Apache-2.0. It adds 924 tokens to every session, about $0.0046 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

sdlc-quality AGENTS.md

Instructions for zircote-plugins/sdlc-quality, covering agents.md - openai codex guidelines, project identity, quick context, agent guidelines and 1. understand the domain model.

zircote-plugins/sdlc-quality · 1,405 tokens

sdlc-quality copilot-instructions.md

Instructions for zircote-plugins/sdlc-quality, covering copilot instructions for sdlc plugin, project overview, repository structure, key conventions and rfc 2119 terminology.

zircote-plugins/sdlc-quality · 1,255 tokens

high-quality-projects-skill AGENTS.md

AGENTS.md instructions for RandyNorthrup/high-quality-projects-skill, covering agents.md, the two workflows, resolving paths, what is in here and non-negotiables when using this package.

RandyNorthrup/high-quality-projects-skill · 1,209 tokens

code-discipline-skills AGENTS.md

Instructions for eliranpv11/code-discipline-skills, covering code discipline, priority order, 1. think before coding, 2. verify reality before acting and 3. simplicity first.

eliranpv11/code-discipline-skills · 1,801 tokens

high-quality-projects-skill copilot-instructions.md

Copilot instructions for RandyNorthrup/high-quality-projects-skill: This repository provides two vendor-neutral workflows for holding a codebase to production standards.

RandyNorthrup/high-quality-projects-skill · 205 tokens

arbiterx CLAUDE.md

Instructions for NeelPrime/arbiterx, covering arbiterx engineering rules, setup, rules (always enforced), never generate and quality gate.

NeelPrime/arbiterx · 237 tokens